© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26843
    Prev
    Next
    INDEX
    Explanations

    instances of the word "align" and related contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.77
    toch
    -0.76
    ijnt
    -0.75
     Mandela
    -0.74
    äumt
    -0.73
    存于互联网档案馆
    -0.73
    routeProvider
    -0.73
    CloseOperation
    -0.72
     AssemblyCulture
    -0.71
     Christo
    -0.71
    POSITIVE LOGITS
    align
    1.34
    er
    0.90
    o
    0.75
    az
    0.68
     Zwick
    0.62
    y
    0.61
    Coo
    0.60
    yaz
    0.59
    mate
    0.58
     kok
    0.57
    Activations Density 0.000%

    No Known Activations